AI100 with Shonit matched manual microscopy on 882 blood smears

In FDA's review of AI100 with Shonit, results on 882 blood smears agreed with manual microscopy, with 92.7% sensitivity and 95.4% specificity for abnormal white cells.

  • Not rated an organization

    The study measured agreement with manual microscopy, and no gain in time or accuracy at any laboratory is reported.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Intended benefit.
Evidence

foundstudiedreportedclaimed

An independent regulatory document supports the benefit.

Compared with

Manual microscopy of the same 882 smears. Measured.

The system’s part
Not isolated. The study compared the device's results with manual microscopy. It did not compare laboratory work with and without the device.
Limits
Not yet checked.
Costs and harms
Not yet checked.
Later
Not yet checked.

Download data Cite Suggest a correction

Benefit type
Repetitive Task Automation
System
AI100 with Shonit
Made by
SigTuple Technologies Pvt. Ltd.
Used by
SigTuple (method comparison against manual microscopy at four sites)
Stage
Tested in a laboratory
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Identifying Objects, Actions, and Events, Processing Information
Collections
Scrutiny and findings
Last revised
31 October 2026

Sources

  1. Regulatory document, by authors with no tie to the system.

    U.S. Food and Drug Administration, Center for Devices and Radiological Health. 510(k) substantial equivalence determination decision summary for AI100 with Shonit (K221309). Cleared 2023-09-19.

    A method comparison study was conducted at four (4) sites comparing the AI100 with Shonit to manual microscopy. A total of 882 samples were collected encompassing healthy subjects and patients with specific disease conditions. Blood samples (K2EDTA) were collected, and one peripheral blood smear (PBS) slide was prepared for each sample (Romanowsky stain). The slides were randomly selected, blinded and evaluated by two examiners at each site. Passing-Bablok Regression analysis was performed for WBC differential and overall agreement, sensitivity and specificity were measured for WBC Distributional and Morphological abnormalities. Overall agreement, sensitivity and specificity were evaluated for RBC and PLT morphology. Calculations of 95% confidence intervals are also provided. The study met the pre-defined acceptance criteria.

Details

AI system

Workflow

Each sample was smeared on a slide and stained with a Romanowsky stain. The device scanned the smear and classified white cells, red cells and platelets on each image.

Follow-up

Conditions for replication

A skilled operator trained on the device reviews the cells and classifies each one. The device is used in a clinical laboratory.

Entry details

Sector

Healthcare.

Purpose

SigTuple built AI100 with Shonit to locate blood cells on peripheral blood smears and present their images for a trained operator to classify.

Not yet checked: model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, AI contribution, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). AI100 with Shonit matched manual microscopy on 882 blood smears (AIBD-0803). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0803.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)

BibTeX Data Field definitions